mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
6b81590c55
Systematic prune per AGENTS.md test policy, one pass over every major test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli, cron, tui_gateway, honcho/openviking, root-level): - DELETE: source-reading tests (read_text/getsource on prod files), change-detector tests (exact catalog counts, model-name snapshots, config version literals), mock-echo tests (assert a mock returns what it was told), assertion-free/trivial tests, near-duplicate parametrizations (boundaries + one representative kept), async/sync twin duplicates, cosmetic within-file variations. - KEEP (mandatory): security/redaction/approval guards, message-role alternation invariants, prompt-caching/deterministic-call-id invariants, issue-number regression tests (deduped), E2E tests. - 6 test files deleted outright (script-style/no-assert or fully redundant); conftest.py, fakes/, fixtures/ untouched. - tests/acp/conftest.py added: autouse fixture stubs the live models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server tests performed on every session create — test_server.py 147s → 3.4s, and the tests are now genuinely hermetic. - Sleep-based slowness shrunk where safe (codex_ttfb_watchdog, compression_concurrent_fork, etc.); no wall-clock assertion tightened. Verification: full hermetic suite via scripts/run_tests.sh — 2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall (baseline: 583s wall, 13,564s subprocess CPU).
31 lines
921 B
Python
31 lines
921 B
Python
"""Tests for shared tool result classification helpers."""
|
|
|
|
import json
|
|
|
|
from agent.tool_result_classification import (
|
|
file_mutation_result_landed,
|
|
)
|
|
|
|
|
|
def test_write_file_with_nested_lint_error_counts_as_landed():
|
|
result = json.dumps({
|
|
"bytes_written": 12,
|
|
"lint": {"status": "error", "output": "SyntaxError: invalid syntax"},
|
|
})
|
|
|
|
assert file_mutation_result_landed("write_file", result) is True
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_side_effect_classification_keeps_session_mutations():
|
|
from agent.tool_result_classification import tool_may_have_side_effect
|
|
|
|
assert tool_may_have_side_effect("todo") is True
|
|
assert tool_may_have_side_effect("memory") is True
|
|
assert tool_may_have_side_effect("write_file") is True
|
|
assert tool_may_have_side_effect("mcp_unknown") is True
|
|
assert tool_may_have_side_effect("read_file") is False
|
|
assert tool_may_have_side_effect("web_search") is False
|